本文選題：農(nóng)田圖像分割 + 顏色因子�。� 參考：《西北農(nóng)林科技大學(xué)》2017年碩士論文

【摘要】：由于受到天氣、溫度和光照等因素的影響,智能農(nóng)業(yè)機(jī)器人感知環(huán)境信息時(shí)會(huì)存在一定的不確定性。為進(jìn)一步提高智能農(nóng)業(yè)機(jī)器人的環(huán)境感知能力,需對不同光照條件下的農(nóng)田圖像進(jìn)行分割。本研究以西北農(nóng)林科技大學(xué)北校區(qū)試驗(yàn)田三葉期至五葉期玉米農(nóng)田圖像為研究對象,采用顏色因子法,結(jié)合閾值分割法和機(jī)器學(xué)習(xí)法實(shí)現(xiàn)了不同光照條件下的農(nóng)田圖像分割,并通過主觀評價(jià)法和客觀評價(jià)法完成算法分析及驗(yàn)證。本研究的主要內(nèi)容和結(jié)論有:(1)農(nóng)田圖像的獲取及分類。為實(shí)現(xiàn)獲取農(nóng)田圖像的自動(dòng)化分類,提出了基于數(shù)學(xué)統(tǒng)計(jì)學(xué)知識分析農(nóng)田圖像直方圖的方法。實(shí)驗(yàn)發(fā)現(xiàn),不同光照條件下農(nóng)田圖像R,G,B顏色通道對應(yīng)的直方圖,其均值指標(biāo)和偏度指標(biāo)在任何區(qū)間上均沒有重合,可作為農(nóng)田圖像自動(dòng)分類的標(biāo)準(zhǔn)。與人工分類方法對比后發(fā)現(xiàn),本文方法分類誤差率最大為10.52%,說明采用上述方法可實(shí)現(xiàn)農(nóng)田圖像的自動(dòng)分類。(2)光照充足或光照偏弱條件下的農(nóng)田圖像分割。針對光照充足條件下農(nóng)田圖像顏色特征較為明顯的特點(diǎn),主要采用直方圖均值法和大津法實(shí)現(xiàn)了農(nóng)田圖像的分割;針對光照偏弱導(dǎo)致農(nóng)田圖像顏色和形狀特征不顯著的特性,主要采用無監(jiān)督學(xué)習(xí)中的模糊C均值聚類算法(FCM)實(shí)現(xiàn)了農(nóng)田圖像的分割。最后完成兩類實(shí)驗(yàn)結(jié)果的剖析比較。由于光照充足和光照偏弱條件下農(nóng)田圖像分割目標(biāo)十分復(fù)雜,因此主要采用了主觀評價(jià)法分析實(shí)驗(yàn)結(jié)果。實(shí)驗(yàn)發(fā)現(xiàn),兩類農(nóng)田圖像分割結(jié)果平均主觀質(zhì)量分?jǐn)?shù)分別為4.26和4.06,則根據(jù)CCIR500五級評分質(zhì)量尺度和妨礙尺度說明,采用本文方法圖像分割質(zhì)量較好,可實(shí)現(xiàn)復(fù)雜農(nóng)田圖像的分割。(3)光照偏強(qiáng)條件下的農(nóng)田圖像分割。針對光照偏強(qiáng)導(dǎo)致大量高光點(diǎn)對圖像分割精度干擾的問題,本文提出采用改進(jìn)的簡單線性迭代聚類算法(SLIC)完成圖像預(yù)處理提取超像素,提取特征向量并通過曲線進(jìn)行初步篩選,然后建立分類器實(shí)現(xiàn)農(nóng)田圖像的分類。分類器主要選擇貝葉斯和支持向量機(jī)(SVM)。實(shí)驗(yàn)發(fā)現(xiàn),改進(jìn)的SLIC在不影響圖像預(yù)處理結(jié)果的前提下可縮短運(yùn)行時(shí)間;SVM總體分類精度優(yōu)于貝葉斯,平均總體分類精度可達(dá)到94.83%,說明采用SVM可有效實(shí)現(xiàn)含大量高光點(diǎn)簡單農(nóng)田圖像分割。以農(nóng)田圖像自動(dòng)分類為研究基礎(chǔ),本文基本完成了不同光照條件下的農(nóng)田圖像分割,為提高智能農(nóng)業(yè)機(jī)器人感知環(huán)境信息能力提供了有力的保障。
[Abstract]:Due to the influence of weather, temperature and light, the intelligent agricultural robot will have some uncertainty when it perceives environmental information. In order to improve the environment perception ability of intelligent agricultural robot, it is necessary to segment farmland images under different illumination conditions. In this study, the field images of maize in three leaf period to five leaf stage in the experimental field of North Campus of Northwestern University of Agriculture and Forestry Science and Technology were studied. Using color factor method, combining threshold segmentation method and machine learning method, the field image segmentation under different illumination conditions was realized. The algorithm is analyzed and verified by subjective evaluation and objective evaluation. The main contents and conclusions of this study are: 1) farmland image acquisition and classification. In order to achieve automatic classification of farmland images, a histogram analysis method based on mathematical statistics was proposed. It was found that the histogram corresponding to the color channel of RDG _ (B) in farmland images under different illumination conditions had no coincidence in any interval, so it could be used as a standard for automatic classification of farmland images. Comparing with the artificial classification method, it is found that the maximum classification error rate of this method is 10.52, which shows that the above method can be used to realize the automatic classification of farmland images with sufficient illumination or weak illumination. In view of the obvious color characteristics of farmland images under sufficient illumination, the histogram mean method and Otsu method are mainly used to segment farmland images, and the weak illumination leads to the characteristics that the color and shape features of farmland images are not significant. The fuzzy C-means clustering algorithm (FCM) in unsupervised learning is used to segment farmland images. Finally, two kinds of experimental results are analyzed and compared. Because the target of farmland image segmentation is very complex under the condition of sufficient illumination and weak illumination, the subjective evaluation method is mainly used to analyze the experimental results. The experimental results show that the average subjective mass scores of the two kinds of farmland images are 4.26 and 4.06, respectively. According to the quality scale and hindrance scale of CCIR500 five-grade score, the image segmentation quality is better by using this method. The segmentation of complex farmland image can be realized under the condition of strong illumination. Aiming at the problem that a large number of high light points interfere with image segmentation accuracy due to the strong illumination, an improved simple linear iterative clustering algorithm (SLICs) is proposed to extract super-pixels, extract feature vectors and screen through curves. Then a classifier is established to realize the classification of farmland images. The classifier mainly selects Bayes and support Vector Machine (SVM). The experimental results show that the improved SLIC can shorten the running time and the overall classification accuracy is better than that of Bayes without affecting the result of image preprocessing. The average overall classification accuracy can reach 94.83, which shows that using SVM can effectively realize the segmentation of simple farmland images with a large number of high light points. Based on the automatic classification of farmland images, the segmentation of farmland images under different illumination conditions is basically completed in this paper, which provides a powerful guarantee for improving the ability of intelligent agricultural robots to perceive environmental information.
【學(xué)位授予單位】：西北農(nóng)林科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：S126;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳曉倩;唐晶磊;苗榮慧;;正態(tài)分布下最小錯(cuò)誤率的變量噴施貝葉斯決策[J];農(nóng)機(jī)化研究;2016年07期

2 劉瓊;史諾;;基于Lab和YUV顏色空間的農(nóng)田圖像分割方法[J];國外電子測量技術(shù);2015年04期

3 夏朝俊;顧春新;李彬;;精準(zhǔn)農(nóng)業(yè)無線傳感器網(wǎng)絡(luò)的研究與實(shí)現(xiàn)[J];機(jī)電工程;2015年03期

4 唐萬;胡俊;張暉;吳攀;賀華;;Kappa系數(shù):一種衡量評估者間一致性的常用方法（英文）[J];上海精神醫(yī)學(xué);2015年01期

5 伍艷蓮;趙力;姜海燕;郭小清;黃芬;;基于改進(jìn)均值漂移算法的綠色作物圖像分割方法[J];農(nóng)業(yè)工程學(xué)報(bào);2014年24期

6 朱軍;胡文波;;貝葉斯機(jī)器學(xué)習(xí)前沿進(jìn)展綜述[J];計(jì)算機(jī)研究與發(fā)展;2015年01期

7 宋艷濤;紀(jì)則軒;孫權(quán)森;;基于圖像片馬爾科夫隨機(jī)場的腦MR圖像分割算法[J];自動(dòng)化學(xué)報(bào);2014年08期

8 孟慶寬;何潔;仇瑞承;馬曉丹;司永勝;張漫;劉剛;;基于機(jī)器視覺的自然環(huán)境下作物行識別與導(dǎo)航線提取[J];光學(xué)學(xué)報(bào);2014年07期

9 畢凱;王曉丹;姚旭;周進(jìn)登;;一種基于Bagging和混淆矩陣的自適應(yīng)選擇性集成[J];電子學(xué)報(bào);2014年04期

10 彭紅星;鄒湘軍;陳麗娟;熊俊濤;陳科尹;林桂潮;;基于雙次Otsu算法的野外荔枝多類色彩目標(biāo)快速識別[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2014年04期

相關(guān)博士學(xué)位論文 前2條

1 張小峰;基于模糊聚類算法的醫(yī)學(xué)圖像分割技術(shù)研究[D];山東大學(xué);2014年

2 汪啟偉;圖像直方圖特征及其應(yīng)用研究[D];中國科學(xué)技術(shù)大學(xué);2014年

相關(guān)碩士學(xué)位論文 前5條

1 于振;基于模糊理論的超像素算法研究及應(yīng)用[D];山東大學(xué);2014年

2 黃秋晗;基于超像素的兩階段圖像分割[D];華南理工大學(xué);2014年

3 李應(yīng)彬;融合深度信息的圖像分割算法研究[D];浙江理工大學(xué);2014年

4 劉春燕;圖像分割評價(jià)方法研究[D];西安電子科技大學(xué);2011年

5 王坤;數(shù)字圖像分割和質(zhì)量評價(jià)方法的研究[D];東北大學(xué);2006年

，

本文編號：1880178